Game Analytics: From Bootstrapping to Predictive Modeling

1. Data Overview & Preprocessing

# Load and clean the data
game_data <- read.csv("data/game_sessions.csv", stringsAsFactors = FALSE)

# Data cleaning and preprocessing
game_data_clean <- game_data %>%
  mutate(
    start_time = as.POSIXct(start_time, format = "%Y-%m-%dT%H:%M:%OSZ"),
    end_time = as.POSIXct(end_time, format = "%Y-%m-%dT%H:%M:%OSZ"),
    death_reason = as.factor(death_reason),
    # Handle missing end_time
    game_duration = ifelse(is.na(game_duration), 0, game_duration),
    # Create performance metrics
    score_per_second = ifelse(game_duration > 0, score / game_duration, 0),
    coins_per_pipe = ifelse(pipes_passed > 0, coins_collected / pipes_passed, 0),
    accuracy = ifelse(bullets_fired > 0, ufos_shot / bullets_fired, 0)
  ) %>%
  filter(!is.na(start_time))  # Remove incomplete records

# Display basic information
cat("Dataset Dimensions:", dim(game_data_clean), "\n")

Dataset Dimensions: 300 13 

cat("Date Range:", as.character(min(game_data_clean$start_time)), "to", 
    as.character(max(game_data_clean$start_time)), "\n")

Date Range: 2025-11-16 12:33:32.897 to 2025-11-17 04:58:20.094 

# Summary statistics
summary_stats <- game_data_clean %>%
  select(score, game_duration, coins_collected, ufos_shot, bullets_fired, pipes_passed) %>%
  summary()

# Display table
game_data_display <- game_data_clean %>%
  mutate(across(where(is.numeric), ~ round(., 2)))

game_data_display %>%
  head(10) %>%
  gt() %>%
  tab_header(
    title = "Game Session Data — Preview (10 rows)"
  ) %>%
  opt_table_font(
    font = google_font("Roboto")
  ) %>%
  cols_align(
    align = "center",
    columns = everything()
  ) %>%
  tab_options(
    table.width = pct(100),
    column_labels.padding = px(6),
    data_row.padding = px(6),
    table.font.size = px(14)
  )

Game Session Data — Preview (10 rows)
id	start_time	end_time	score	coins_collected	ufos_shot	bullets_fired	death_reason	game_duration	pipes_passed	score_per_second	coins_per_pipe	accuracy
plane_1763296412897	2025-11-16 12:33:32.897	2025-11-16 12:33:40.65	8	2	2	33	pipe	7	3	1.14	0.67	0.06
plane_1763296421212	2025-11-16 12:33:41.212	2025-11-16 12:33:44.999	6	0	2	31	pipe	3	1	2.00	0.00	0.06
plane_1763296425226	2025-11-16 12:33:45.226	2025-11-16 12:33:45.949	0	0	0	0	ground	0	0	0.00	0.00	0.00
plane_1763296426741	2025-11-16 12:33:46.741	2025-11-16 12:33:47.465	0	0	0	0	ground	0	0	0.00	0.00	0.00
plane_1763296427702	2025-11-16 12:33:47.702	2025-11-16 12:33:48.415	0	0	0	0	ground	0	0	0.00	0.00	0.00
plane_1763296428948	2025-11-16 12:33:48.948	2025-11-16 12:33:49.665	0	0	0	0	ground	0	0	0.00	0.00	0.00
plane_1763296429950	2025-11-16 12:33:49.95	2025-11-16 12:33:54.182	6	0	2	25	pipe	4	2	1.50	0.00	0.08
plane_1763296435012	2025-11-16 12:33:55.012	2025-11-16 12:33:55.732	0	0	0	0	ground	0	0	0.00	0.00	0.00
plane_1763296435967	2025-11-16 12:33:55.967	2025-11-16 12:33:56.699	0	0	0	0	ground	0	0	0.00	0.00	0.00
plane_1763296437259	2025-11-16 12:33:57.259	2025-11-16 12:34:01.782	7	1	2	41	pipe	4	2	1.75	0.50	0.05

2. Exploratory Data Analysis

2.1 Distribution of Key Metrics

# Create distribution plots
p1 <- ggplot(game_data_clean, aes(x = score)) +
  geom_histogram(fill = "steelblue", alpha = 0.7, bins = 30) +
  labs(title = "Score Distribution", x = "Score", y = "Frequency") +
  theme_minimal()

p2 <- ggplot(game_data_clean, aes(x = game_duration)) +
  geom_histogram(fill = "darkorange", alpha = 0.7, bins = 30) +
  labs(title = "Game Duration Distribution", x = "Duration (seconds)", y = "Frequency") +
  theme_minimal()

p3 <- ggplot(game_data_clean, aes(x = pipes_passed)) +
  geom_histogram(fill = "forestgreen", alpha = 0.7, bins = 30) +
  labs(title = "Pipes Passed Distribution", x = "Pipes Passed", y = "Frequency") +
  theme_minimal()

p4 <- ggplot(game_data_clean, aes(x = coins_collected)) +
  geom_histogram(fill = "goldenrod", alpha = 0.7, bins = 30) +
  labs(title = "Coins Collected Distribution", x = "Coins", y = "Frequency") +
  theme_minimal()

ggarrange(p1, p2, p3, p4, ncol = 2, nrow = 2)

2.2 Death Reason Analysis

death_summary <- game_data_clean %>%
  group_by(death_reason) %>%
  summarise(
    count = n(),
    percentage = n() / nrow(game_data_clean) * 100,
    avg_score = mean(score),
    avg_duration = mean(game_duration)
  ) %>%
  arrange(desc(count))

# Visualization
p_death <- ggplot(death_summary, aes(x = reorder(death_reason, -count), y = count, fill = death_reason)) +
  geom_bar(stat = "identity", alpha = 0.8) +
  geom_text(aes(label = paste0(round(percentage, 1), "%")), vjust = -0.5) +
  labs(title = "Death Reason Distribution", 
       x = "Death Reason", 
       y = "Count") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

p_death_score <- ggplot(game_data_clean, aes(x = death_reason, y = score, fill = death_reason)) +
  geom_boxplot(alpha = 0.7) +
  labs(title = "Score by Death Reason", x = "Death Reason", y = "Score") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

ggarrange(p_death, p_death_score, ncol = 2)